| { | |
| "best_metric": 0.2479654848575592, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4294149221685454, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008588298443370907, | |
| "grad_norm": 7.427453517913818, | |
| "learning_rate": 5e-05, | |
| "loss": 9.1228, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008588298443370907, | |
| "eval_loss": 9.084851264953613, | |
| "eval_runtime": 3.6711, | |
| "eval_samples_per_second": 13.62, | |
| "eval_steps_per_second": 3.541, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017176596886741814, | |
| "grad_norm": 7.320578098297119, | |
| "learning_rate": 0.0001, | |
| "loss": 8.8094, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02576489533011272, | |
| "grad_norm": 7.477211952209473, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.7855, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03435319377348363, | |
| "grad_norm": 7.261955738067627, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.9701, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04294149221685454, | |
| "grad_norm": 6.757033348083496, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 5.0192, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05152979066022544, | |
| "grad_norm": 5.1992506980896, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.062, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06011808910359635, | |
| "grad_norm": 4.475039482116699, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.0144, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06870638754696726, | |
| "grad_norm": 4.5666117668151855, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.4798, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07729468599033816, | |
| "grad_norm": 3.4243249893188477, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.687, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08588298443370908, | |
| "grad_norm": 2.7240149974823, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.022, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09447128287707998, | |
| "grad_norm": 2.1973557472229004, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.8649, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10305958132045089, | |
| "grad_norm": 2.913463592529297, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.8563, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11164787976382179, | |
| "grad_norm": 3.2875776290893555, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.7253, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1202361782071927, | |
| "grad_norm": 2.7548460960388184, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.4595, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1288244766505636, | |
| "grad_norm": 2.3721401691436768, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.3879, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1374127750939345, | |
| "grad_norm": 2.5925698280334473, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.3775, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14600107353730543, | |
| "grad_norm": 2.4489991664886475, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.3197, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15458937198067632, | |
| "grad_norm": 1.0083777904510498, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.2952, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16317767042404724, | |
| "grad_norm": 1.3845618963241577, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.2963, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17176596886741816, | |
| "grad_norm": 1.289259433746338, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.2785, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18035426731078905, | |
| "grad_norm": 1.1156764030456543, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.3111, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18894256575415996, | |
| "grad_norm": 1.0241203308105469, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.3082, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 1.4435569047927856, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.3446, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20611916264090177, | |
| "grad_norm": 1.137935757637024, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.3731, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2147074610842727, | |
| "grad_norm": 0.5288839936256409, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.3305, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2147074610842727, | |
| "eval_loss": 0.301417738199234, | |
| "eval_runtime": 3.3294, | |
| "eval_samples_per_second": 15.018, | |
| "eval_steps_per_second": 3.905, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22329575952764358, | |
| "grad_norm": 5.314520835876465, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.3691, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2318840579710145, | |
| "grad_norm": 1.5764119625091553, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.3472, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2404723564143854, | |
| "grad_norm": 1.4415510892868042, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.343, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2490606548577563, | |
| "grad_norm": 1.1646080017089844, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.3098, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2576489533011272, | |
| "grad_norm": 0.6379237174987793, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.294, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.26623725174449814, | |
| "grad_norm": 0.4787558615207672, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.2771, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.274825550187869, | |
| "grad_norm": 1.1004618406295776, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.2637, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2834138486312399, | |
| "grad_norm": 0.5449252128601074, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.2707, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.29200214707461086, | |
| "grad_norm": 1.1775004863739014, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.3555, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.30059044551798175, | |
| "grad_norm": 0.8506811857223511, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.2903, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.30917874396135264, | |
| "grad_norm": 1.2801744937896729, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.3428, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3177670424047236, | |
| "grad_norm": 1.0148999691009521, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.3404, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3263553408480945, | |
| "grad_norm": 0.9798362851142883, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.3151, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.33494363929146537, | |
| "grad_norm": 2.059889554977417, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.3205, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3435319377348363, | |
| "grad_norm": 2.1281702518463135, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.3427, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3521202361782072, | |
| "grad_norm": 0.7399386167526245, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.284, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3607085346215781, | |
| "grad_norm": 0.8385106325149536, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.2985, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.369296833064949, | |
| "grad_norm": 0.4932496249675751, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.2779, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3778851315083199, | |
| "grad_norm": 0.8921447396278381, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.3136, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3864734299516908, | |
| "grad_norm": 0.7302391529083252, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.2885, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.5096395015716553, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.2812, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.40365002683843265, | |
| "grad_norm": 0.7803435325622559, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.2857, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.41223832528180354, | |
| "grad_norm": 0.9682196378707886, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.3371, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.42082662372517443, | |
| "grad_norm": 1.1506094932556152, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.3735, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4294149221685454, | |
| "grad_norm": 0.6556252837181091, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3252, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4294149221685454, | |
| "eval_loss": 0.2479654848575592, | |
| "eval_runtime": 3.3272, | |
| "eval_samples_per_second": 15.028, | |
| "eval_steps_per_second": 3.907, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.32019209568256e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |